This is the PyTorch implementation of ``FCN+: Global Receptive Convolution Makes FCN Great Again'' which has been accepted to NeuroComputing. NeuroComputing version, ArXiv version. Our FCN+ is built ...
Abstract: In this paper, a CNN hardware accelerator for standard convolution and depthwise convolution is proposed. The accelerator can support two different data flow modes. A computation array ...
Abstract: Existing convolutional neural network-based reversible data hiding (RDH) predictors typically stack the standard convolution blocks with stride 1 for feature extraction, and keep the sizes ...
Please Note: All times UK. Tables are subject to change. The BBC is not responsible for any changes that may be made. Manager: Frédéric Vanderbiest Formation: 3 - 4 - 1 - 2 Manager: Vincent Euvrard ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results